Google launches Flex and Priority tiers for Gemini API
google added flex and priority inference tiers to the gemini api. flex cuts costs by 50% for background tasks by downgrading criticality, while priority offers high reliability for interactive apps. both use standard synchronous endpoints, eliminating the need for async batch api management. flex is available to all paid users, priority requires tier 2 or 3 projects.
Google introduced Flex and Priority inference tiers to the Gemini API, allowing developers to optimize costs and reliability through a unified interface. Flex Inference offers 50% savings compared to Standard pricing for latency-tolerant workloads like data enrichment or agentic background processes, utilizing a synchronous interface to bypass batch management complexity. Priority Inference targets high-reliability needs for user-facing applications, ensuring traffic is not preempted during peak loads with automatic graceful downgrades to Standard tier upon exceeding limits.